Related Models
Pricing
Input
$0.07
per 1M tokens
Output
$0.19
per 1M tokens
Blended
$0.10
per 1M tokens
Cheaper than 83% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.10
Monthly
$3.12
vs. Similar Models
Google: Gemini 2.5 Flash LiteQ:0.0
$0.17+68%
Hermes 4 - Llama-3.1 70B (Non-reasoning)Q:0.0
$0.20+90%
Nova LiteQ:0.0
$0.10+1%
OpenAI: GPT-4o-miniQ:0.0
$0.26+152%
Performance
150
tokens/sec
Faster than 75% of models
0.56
seconds
Faster than 81% of models
0.56
seconds
Faster than 87% of models
Market Median
94 tok/s
60% faster
Median TTFT
1.10s
49% faster
Throughput/Dollar
1442
tok/s per $/1M
Speed Comparison
Mistral Small (Sep '24)
150 tok/s+0%
Mistral Small 3.2
149 tok/s-0%
Apriel-v1.5-15B-Thinker
151 tok/s+0%
Benchmarks
MMLU-Pro
65.2%
GPQA Diamond
46.2%
HLE
4.1%
LiveCodeBench
25.2%
SciCode
23.6%
TerminalBench HardNot evaluated
MATH-500
71.5%
AIME
8.0%
AIME 2025
4.3%
IFBench
26.4%
Long Context Recall
0.0%
Tau2
19.6%
Market AverageTop Score